Instructions to use NorGLM/NorGPT-3B-continue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NorGLM/NorGPT-3B-continue with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="NorGLM/NorGPT-3B-continue")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NorGLM/NorGPT-3B-continue")
model = AutoModelForCausalLM.from_pretrained("NorGLM/NorGPT-3B-continue", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NorGLM/NorGPT-3B-continue with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NorGLM/NorGPT-3B-continue"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorGLM/NorGPT-3B-continue",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NorGLM/NorGPT-3B-continue

SGLang

How to use NorGLM/NorGPT-3B-continue with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "NorGLM/NorGPT-3B-continue" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorGLM/NorGPT-3B-continue",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "NorGLM/NorGPT-3B-continue" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NorGLM/NorGPT-3B-continue",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NorGLM/NorGPT-3B-continue with Docker Model Runner:
```
docker model run hf.co/NorGLM/NorGPT-3B-continue
```

NorGPT-3B-continue

Commit History

Mar 26, 2024

09:43
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
5dfdef0

Mar 11, 2024

00:17
Update README.md

NorGLM

Verified signature
564f4d3
00:10
Update README.md

NorGLM

Verified signature
4a66808

Mar 10, 2024

19:52
Update README.md

NorGLM

Verified signature
99a7c3f

Mar 8, 2024

16:59
Upload 5 files

NorGLM

Verified signature
09aa089
16:32
Update README.md

NorGLM

Verified signature
1e12a7e
16:29
initial commit

NorGLM

Verified signature
8d40846

Commit History

Mar 26, 2024

Adding `safetensors` variant of this model⁠

Mar 11, 2024

Update README.md

Update README.md

Mar 10, 2024

Update README.md

Mar 8, 2024

Upload 5 files

Update README.md

initial commit